nutrient-document-processing

Automates document conversion, extraction, OCR, redaction, signing, and form filling via Nutrient DWS API.

1|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/aleonsa/claude-config --skill nutrient-document-processing-aleonsa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nutrient-document-processing
Source: https://github.com/aleonsa/claude-config/tree/main/claude/skills/nutrient-document-processing
Command: npx skills add https://github.com/aleonsa/claude-config --skill nutrient-document-processing-aleonsa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines document management by automating conversion, text extraction, OCR, redaction, signing, and form filling through the Nutrient DWS API.

Core Features & Use Cases

  • Format Conversion: Effortlessly convert between various document types (PDF, DOCX, XLSX, PPTX, HTML, images).
  • Intelligent Extraction: Extract plain text or structured tables from documents.
  • OCR Capabilities: Make scanned documents searchable with advanced OCR.
  • Data Redaction: Securely remove sensitive information using presets or custom regex.
  • Digital Signing & Form Filling: Add digital signatures and programmatically fill PDF forms.
  • Use Case: Automatically convert a batch of scanned invoices (images) into a searchable PDF, extract the key data into an Excel sheet, and redact any sensitive customer information before archiving.

Quick Start

Use the nutrient-document-processing skill to convert the attached file 'report.docx' to 'report.pdf'.

Frequently Asked Questions about nutrient-document-processing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert DOCX or image files into PDF format?

You can convert DOCX, XLSX, PPTX, HTML, and images to PDF using automated document processing. The Skill handles format conversion directly through the Nutrient DWS API, allowing you to specify input files and target output formats for immediate results.

How do I extract text and tables from a scanned PDF?

Text extraction and table extraction from scanned PDFs are handled through advanced multi-language OCR. This process makes scanned documents searchable and extracts structured data directly from the file content.

What is the best way to redact sensitive information in a PDF?

Data redaction secures PDFs by removing sensitive information using presets or custom regex patterns. You can apply pattern-based redaction programmatically to ensure sensitive data is securely masked before document archiving or distribution.

Can I programmatically fill PDF forms and add digital signatures?

Yes, you can programmatically fill PDF forms and add digital signatures. The Skill automates adding digital signatures and populating form fields directly through the Nutrient DWS API for secure document finalization.

Does OCR support multiple languages for scanned document conversion?

Yes, advanced OCR supports multiple languages for scanned document conversion. You can process scanned images in various languages to make them searchable, extract data, and convert them into formats like PDF.

What file formats are supported for document conversion and extraction?

Supported formats include PDF, DOCX, XLSX, PPTX, HTML, and images. You can convert between these types, extract text or tables, and process scanned documents with OCR across this wide range of input formats.